{"url":"/dataset/imcpt-sparsegm-100","name":"IMCPT-SparseGM-100","full_name":null,"description_markdown":"IMCPT-SparseGM dataset is a new visual graph matching benchmark addressing partial matching and graphs with larger sizes, based on the novel stereo benchmark [Image Matching Challenge PhotoTourism  (IMC-PT)  2020](https://www.cs.ubc.ca/research/image-matching-challenge/2020/). This dataset is released in CVPR 2023 paper [*Deep Learning of Partial Graph Matching via Differentiable Top-K*](https://openreview.net/forum?id=4OoXQPGd1s).\r\n\r\n| **# images** | **# classes** | **avg # nodes** | **avg # edges** | **# universe** | **partial rate** |\r\n| ------------ | ------------- | --------------- | ----------- | -------------- | ---------------- |\r\n| 25765        | 16            | 44.48           | 123.99      | 100            | 55.5%            |","description_withheld":null,"homepage":"https://github.com/Thinklab-SJTU/IMCPT-SparseGM-dataset","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/deep-learning-of-partial-graph-matching-via","title":"Deep Learning of Partial Graph Matching via Differentiable Top-K","first_author":"Runzhong Wang","url":null},"license":null,"modalities":[{"name":"Graphs","url":"/datasets/modality/graphs"}],"tasks":[{"name":"Graph Matching","url":"/task/graph-matching","datasets_with_task":"/datasets/task/graph-matching"},{"name":"Stereo Matching","url":"/task/stereo-matching-1","datasets_with_task":"/datasets/task/stereo-matching-1"},{"name":"Graph Mining","url":"/task/graph-mining","datasets_with_task":"/datasets/task/graph-mining"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["IMCPT-SparseGM-100"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/graph-matching-on-imcpt-sparsegm-100","task":"Graph Matching","dataset_variant":"IMCPT-SparseGM-100","rows":6,"metrics":["F1 score"],"first_row_in_archive_order":{"model":"GCAN-AFAT-U","paper":"/paper/deep-learning-of-partial-graph-matching-via","metrics":{"F1 score":"0.715"},"code_links":[{"title":"Thinklab-SJTU/ThinkMatch","url":"https://github.com/Thinklab-SJTU/ThinkMatch"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/deep-learning-of-partial-graph-matching-via","title":"Deep Learning of Partial Graph Matching via Differentiable Top-K","date":"2023-01-01","rows_on_this_dataset":6,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}